Imagen de Portada

Distributional Spectral Diagnostics for Localizing Grokking Transitions

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Ziyue, Ying, Yufeng, Kanamori, Takafumi
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test
por: Li, Ziyue, et al.
Publicado: (2025)

A Convex Framework for Confounding Robust Inference
por: Ishikawa, Kei, et al.
Publicado: (2023)

Robust Estimation for Kernel Exponential Families with Smoothed Total Variation Distances
por: Kanamori, Takafumi, et al.
Publicado: (2024)

Mixture Proportion Estimation and Weakly-supervised Kernel Test for Conditional Independence
por: Hirose, Yushi, et al.
Publicado: (2026)

Grokking as a Variance-Limited Phase Transition: Spectral Gating and the Epsilon-Stability Threshold
por: Acharya, Pratyush, et al.
Publicado: (2026)

TULiP: Test-time Uncertainty Estimation via Linearization and Weight Perturbation
por: Zhang, Yuhui, et al.
Publicado: (2025)

Grokking as a Falsifiable Finite-Size Transition
por: Bi, Yuda, et al.
Publicado: (2026)

To Grok Grokking: Provable Grokking in Ridge Regression
por: Xu, Mingyue, et al.
Publicado: (2026)

Grokking as Dimensional Phase Transition in Neural Networks
por: Wang, Ping
Publicado: (2026)

SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps
por: Gu, Jiawei, et al.
Publicado: (2025)

Grokking as the Transition from Lazy to Rich Training Dynamics
por: Kumar, Tanishq, et al.
Publicado: (2023)

Scaling-based Data Augmentation for Generative Models and its Theoretical Extension
por: Koike, Yoshitaka, et al.
Publicado: (2024)

The Complexity Dynamics of Grokking
por: DeMoss, Branton, et al.
Publicado: (2024)

Measuring Sharpness in Grokking
por: Miller, Jack, et al.
Publicado: (2024)

Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics
por: Verma, Lucky
Publicado: (2026)

Topological Signatures of Grokking
por: Tang, Yifan, et al.
Publicado: (2026)

Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks
por: Minegishi, Gouki, et al.
Publicado: (2023)

Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition
por: Clauw, Kenzo, et al.
Publicado: (2024)

Feature Repulsion and Spectral Lock-in: An Empirical Study of Two-Layer Network Grokking
por: Xu, Yongzhong
Publicado: (2026)

Grokked Models are Better Unlearners
por: Liang, Yuanbang, et al.
Publicado: (2025)

Grokking as a First Order Phase Transition in Two Layer Networks
por: Rubin, Noa, et al.
Publicado: (2023)

ILDR: Geometric Early Detection of Grokking
por: Golwala, Shreel
Publicado: (2026)

Exploring Grokking: Experimental and Mechanistic Investigations
por: Qiye, Hu, et al.
Publicado: (2024)

GrokAlign: Geometric Characterisation and Acceleration of Grokking
por: Walker, Thomas, et al.
Publicado: (2025)

Grokking in Linear Models for Logistic Regression
por: Das, Nataraj, et al.
Publicado: (2026)

Grokking Explained: A Statistical Phenomenon
por: Carvalho, Breno W., et al.
Publicado: (2025)

Controlling Grokking with Nonlinearity and Data Symmetry
por: Salah, Ahmed, et al.
Publicado: (2024)

Grokking of Diffusion Models: Case Study on Modular Addition
por: Kim, Joon Hyeok, et al.
Publicado: (2026)

Explaining Grokking in Transformers through the Lens of Inductive Bias
por: Singh, Jaisidh, et al.
Publicado: (2026)

Beyond Progress Measures: Theoretical Insights into the Mechanism of Grokking
por: Gu, Zihan, et al.
Publicado: (2025)

Grokking Finite-Dimensional Algebra
por: Notsawo, Pascal Jr Tikeng, et al.
Publicado: (2026)

Grokking Group Multiplication with Cosets
por: Stander, Dashiell, et al.
Publicado: (2023)

Muon Optimizer Accelerates Grokking
por: Tveit, Amund, et al.
Publicado: (2025)

Robust VAEs via Generating Process of Noise Augmented Data
por: Irobe, Hiroo, et al.
Publicado: (2024)

The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology
por: Yıldırım, Alper
Publicado: (2026)

Explaining Grokking and Information Bottleneck through Neural Collapse Emergence
por: Sakamoto, Keitaro, et al.
Publicado: (2025)

Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking
por: Pasand, Ali Saheb, et al.
Publicado: (2025)

Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking
por: Han, Ting, et al.
Publicado: (2025)

When Data Falls Short: Grokking Below the Critical Threshold
por: Singh, Vaibhav, et al.
Publicado: (2025)

Deep Grokking: Would Deep Neural Networks Generalize Better?
por: Fan, Simin, et al.
Publicado: (2024)